Today we're announcing our Series C alongside some big updates that make @meetgranola better for your team and your tools.
Excited to partner with Danny at Index and Mamoon at KP. Big things to come. Back to work!
There are some tweets out there saying that Granola is trying to lock down access to your data.
Tldr; we are actually trying to become more open, not closed. We’re launching a public API next week to complement our MCP. Read on for context.
A couple months ago, we noticed that some folks had reversed engineered our local cache so they could access their meeting data.
Our cache was not built for this (it can change at any point), so we launched our MCP to serve this need. The MCP gives full access to your notes and transcripts (all time for paid users, time restricted for free users). MCP usage has exploded since launch, so we felt good about it.
A week ago, we updated how we store data in our cache and broke the workarounds. This is on us. Stupidly, we thought we had solved these use cases well enough with our MCP.
We’ve now learned that while MCPs are great for connecting to tools like Claude or chatGPT, they don’t meet your needs for agents running locally or for data export / pipeline work.
So we’re going to fix this for you ASAP. First, we’ll launch a public API next week to make it easier for you to pull your data.
Second, we’ll figure out how to make Granola work better for agents running locally. Whether that’s expanding our MCP, launching a CLI, a local API, etc. The industry is moving quickly here, so we’d appreciate your suggestions.
We want Granola data to be accessible and useful wherever you need it. Stay tuned.
So @meetgranola released their official MCP server roughly a year after MCP became a thing. I just ran a side-by-side comparison against our my meeting intelligence pipeline — the results aren't even close.
The design is exceptionally well thought out — particularly the semantic query tool with inline citations. This is a case study in "taking your time to do it right."
The Past
My old approach to ingesting meeting intelligence into Claude:
1. Query Notion database (Granola syncs there)
2. Get page IDs back
3. Fetch each page individually
4. Parse Notion markdown
5. Extract insights from raw text
That's 4-5 API calls per meeting. For 19 meetings, you're looking at ~80+ calls.
The Future
With Granola's MCP: "What key decisions were made this week?"
Returns: Synthesized intelligence with inline citation links to each source meeting.
That's it. One call. Done.
What makes this MCP exceptionally well-designed:
• 4 tools total (list, query, get, transcript). No bloat.
• Semantic search with citations built in — not bolted on
• Participant data pre-resolved ("Laura from Descript", not raw emails)
• Summaries are structured, not raw transcript dumps
Granola didn't ship "get_note_by_id" and call it a day. They built semantic intelligence into the protocol layer.
Bravo. Really impressed and already updated my agents (which was mostly a drastic reduction in instructions meant to manage the complexity of extracting info from the Notion db) and added a new skill so Claude Code can reference meeting discussions on demand.
Here's what @claudeai had to say after testing both approaches on the same set of meetings:
"This will replace 80% of the apps that you have on your phone."
Here's my new episode with @steipete where he showed me:
✅ His personal OpenClaw use cases - flight check-in, home security, and much more
✅ His counterintuitive AI coding workflow - no plan mode, no MCPs, and no fancy prompts
✅ Practical advice for other builders and how to build product taste
Some quotes from Peter:
"It's like having a new weird friend that is also really smart and resourceful that lives on your computer."
"Why should I use MyFitnessPal when I have an infinitely resourceful assistant that already knows I'm making bad decisions at KFC?"
"I don't use MCPs or any of that crap. Just because you can build everything doesn't mean you should."
📌 Watch now: https://t.co/ovYUSg9tP6
Thanks to our sponsors:
@meetgranola - The best AI meeting notes app I've ever used: https://t.co/MNToIh5WTm
@Replit - Create beautiful prototypes and full stack apps: https://t.co/w6kab0zMqN
Granola has an MCP! It works with ChatGPT / Claude / whatever tool you want. Thanks for being patient 🙏🏼
(Hope everyone enjoys this change even more than the one we did on Monday 😅)
@lovable is quickly becoming my favorite AI tool. You can create any SaaS you need, for yourself. No more inbox or spreadsheet chaos. For non-technical professionals, it's a game changer
Introducing Eleven Music. The highest quality AI music model.
- Complete control over genre, style, and structure
- Multi-lingual, including English, Spanish, German, Japanese and more
- Edit the sound and lyrics of individual sections or the whole song
Eleven v3 Alpha is a ChatGPT moment for text-to-speech.
This AI model turns plain text into studio-quality voice acting in 70 + languages expressively.
10 wild examples:
What a crazy week in AI 🤯
- ElevenLabs v3
- Runner H Agent
- Leo AI gets Veo 3
- Mirage Studio AI Actors
- Google’s Gemini 2.5 Pro
- HeyGen IV new AI Studio
- OpenAI Data Connectors
- Google Phone App Local AI
- Mistral Vibe Coding Assistant
Here’s EVERYTHING you need to know:
I'm speechless...
This is a major step-change in AI generated voice (TTS)
Elevenlabs just released v3 as a public alpha and you can try it now for 80% off during all of June 💸
Let's unpack this 👇
Introducing Eleven v3 (alpha) - the most expressive Text to Speech model ever.
Supporting 70+ languages, multi-speaker dialogue, and audio tags such as [excited], [sighs], [laughing], and [whispers].
Now in public alpha and 80% off in June.